Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 5299
    Prev
    Next
    INDEX
    Explanations

    satellite communication and networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的
    0.91
     крайней
    0.77
     κά
    0.75
     sostenible
    0.70
    दी
    0.69
     комплект
    0.68
    seekers
    0.68
    ર
    0.68
    也
    0.67
     किनारे
    0.66
    POSITIVE LOGITS
     satellites
    1.20
     satellite
    1.16
     Satellite
    1.04
    т
    0.95
    н
    0.90
    Satellite
    0.89
     for
    0.88
    卫星
    0.88
     sats
    0.84
    X
    0.83
    Activations Density 0.004%

    No Known Activations